Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
fastapi==0.115.5
uvicorn[standard]==0.32.1
# CPU rembg: the deployed service has no GPU, and the [gpu] extra pulls
# onnxruntime-gpu plus its CUDA libraries on top of the CPU runtime that rembg
# already installs. onnxruntime is pinned because rembg leaves it open, which
# made every rebuild a different inference runtime.
# 2.0.75 was the first release with the fixes for the model_path traversal and
# the server SSRF/CORS advisories. 2.0.86 is the first release that allows
# Pillow 13 (every earlier one caps it below 13), which the Pillow pin below
# needs. It needs Python 3.11 and numpy 2.3, which this python:3.11-slim image
# takes cleanly (onnxruntime 1.28 ships numpy 2 wheels).
rembg==2.0.86
onnxruntime==1.28.0
# Pillow 13.0.0, the same pin every other worker carries. This service decodes an
# image the caller supplied, which is the exact path the heap overflows in the
# JPEG, TIFF and FlashPix loaders and the Ghostscript EPS argument injection
# live on, and 13.0.0 is where OSV lists the fix for all of them.
# `npm run audit:deps` is what surfaces the next one.
Pillow==13.0.0
google-cloud-storage==2.19.0
httpx==0.27.2
pydantic==2.10.3